Very Long Natural Scenery Image Prediction by Outpainting

By Zongxin Yang, Jian Dong, Ping Liu, Yi Yang, Shuicheng Yan. 2019

99 citations recorded by the source corpus.

Comparing to image inpainting, image outpainting receives less attention due to two challenges in it. The first challenge is how to keep the spatial and content consistency between generated images and original input. The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input. To solve the two problems, we devise some innovative modules, named Skip Horizontal Connection and Recurrent Content Transfer, and integrate them into our designed encoder-decoder structure. By this design, our network can generate highly realistic outpainting prediction effectively and efficiently. Other than that, our method can generate new images with very long sizes while keeping the same style and semantic content as the given input. To test the effectiveness of the proposed architecture, we collect a new scenery dataset with diverse, complicated natural scenes. The experimental results on this dataset have demonstrated the efficacy of our proposed network.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (2021, background): “…al., 2019a; Nazeri et al., 2019; Ren et al., 2019; Sagong et al., 2019; Wang et al., 2018; Xie et al., 2019; Xiong et al., 2019; Yan et al., 2018; Yang et al., 2017; 2019a; Yu et al., 2018; Yu et al., 2019; Zeng et al., 2019; Lahiri et al., 2020; Zhao et al., 2020a; Li et al., 2020; Zhou et al.,…”
Palette: Image-to-Image Diffusion Models (2021, methodology): “2019], but are often domain-specific [Bowen et al. 2021; Cheng et al. 2021; Lin et al. 2021; Wang et al. 2019a; Yang et al. 2019a].”
InfinityGAN: Towards Infinite-Resolution Image Synthesis (2021, methodology): “In Table 2, our model performs favorably against all baselines in image outpainting (Boundless [34], NS-outpaint [40], and In&Out [4]).”
InOut: Diverse Image Outpainting via GAN Inversion (2021, methodology): “In contrast, Boundless [27] tends to introduce raindrop-shaped artifacts, DeepFillv2 [33, 34] creates blurry extensions, while NSoutpaint [31] and Image2stylegan++ [2] frequently generates strong artifacts and obvious color differences.”